The use of nuclear morphometry for the prediction of survival in patients with advanced cancer of the larynx

LPCANet: Classification of Laryngeal Cancer Histopathological Images Using a CNN with Position Attention and Channel Attention Mechanisms

Laryngeal cancer is one of the most common malignant tumors in otolaryngology, and histopathological image analysis is the gold standard for the diagnosis of laryngeal cancer. However, pathologists have high subjectivity in their diagnoses, which makes it easy to miss diagnoses and misdiagnose. In addition, according to a literature search, there is currently no computer-aided diagnosis (CAD) algorithm that has been applied to the classification of histopathological images of laryngeal cancer. Convolutional neural networks (CNNs) are widely used in various other cancer classification tasks. However, the potential global and channel relationships of images may be ignored, which will affect the feature representation ability. Simultaneously, due to the lack of interpretability, the results are often difficult to accept by pathologists. we propose a laryngeal cancer classification network (LPCANet) based on a CNN and attention mechanisms. First, the original histopathological images are sequentially cropped into patches. Then, the patches are input into the basic ResNet50 to extract the local features. Then, a position attention module and a channel attention module are added in parallel to capture the spatial dependency and the channel dependency, respectively. The two modules produce the fusion feature map to enhance the feature representation and improve network classification performance. Moreover, the fusion feature map is extracted and visually analyzed by the grad-weighted class activation map (Grad_CAM) to provide a certain interpretability for the final results. The three-class classification performance of LPCANet is better than those of the five state-of-the-art classifiers (VGG16, ResNet50, InceptionV3, Xception and DenseNet121) on the two original resolutions (534 * 400 and 1067 * 800). On the 534 * 400 data, LPCANet achieved 73.18% accuracy, 74.04% precision, 73.15% recall, 72.9% F1-score, and 0.8826 AUC. On the 1067 * 800 data, LPCANet achieved 83.15% accuracy, 83.5% precision, 83.1% recall, 83.1% F1-score, and 0.9487 AUC. The results show that LPCANet enhances the feature representation by capturing the global and channel relationships and achieves better classification performance. In addition, the visual analysis of Grad_CAM makes the results interpretable, which makes it easier for the results to be accepted by pathologists and allows the method to become a second tool for auxiliary diagnosis.

Programmed death-ligand 1 expression by digital image analysis advances thyroid cancer diagnosis among encapsulated follicular lesions

Recognition of noninvasive follicular thyroid neoplasms with papillary-like nuclear features (NIFTP) that distinguishes them from invasive malignant encapsulated follicular variant of papillary thyroid carcinoma (EFVPTC) can prevent overtreatment of NIFTP patients. We and others have previously reported that programmed death-ligand 1 (PD-L1) is a useful biomarker in thyroid tumors; however, all reports to date have relied on manual scoring that is time consuming as well as subject to individual bias. Consequently, we developed a digital image analysis (DIA) protocol for cytoplasmic and membranous stain quantitation (ThyApp) and evaluated three tumor sampling methods [Systemic Uniform Random Sampling, hotspot nucleus, and hotspot nucleus/3,3'-Diaminobenzidine (DAB)]. A patient cohort of 153 cases consisting of 48 NIFTP, 44 EFVPTC, 26 benign nodules and 35 encapsulated follicular lesions/neoplasms with lymphocytic thyroiditis (LT) was studied. ThyApp quantitation of PD-L1 expression revealed a significant difference between invasive EFVPTC and NIFTP; but none between NIFTP and benign nodules. ThyApp integrated with hotspot nucleus tumor sampling method demonstrated to be most clinically relevant, consumed least processing time, and eliminated interobserver variance. In conclusion, the fully automatic DIA algorithm developed using a histomorphological approach objectively quantitated PD-L1 expression in encapsulated thyroid neoplasms and outperformed manual scoring in reproducibility and higher efficiency.

Microscopy image analysis of p63 immunohistochemically stained laryngeal cancer lesions for predicting patient 5-year survival

The aim of the present study was to design a microscopy image analysis (MIA) system for predicting the 5-year survival of patients with laryngeal squamous cell carcinoma, employing histopathology images of lesions, which had been immunohistochemically (IHC) stained for p63 expression. Biopsy materials from 42 patients, with verified laryngeal cancer and follow-up, were selected from the archives of the University Hospital of Patras, Greece. Twenty six patients had survived more than 5 years and 16 less than 5 years after the first diagnosis. Histopathology images were IHC stained for p63 expression. Images were first processed by a segmentation method for isolating the p63-expressed nuclei. Seventy-seven features were evaluated regarding texture, shape, and physical topology of nuclei, p63 staining, and patient-specific data. Those features, the probabilistic neural network classifier, the leave-one-out (LOO), and the bootstrap cross-validation methods, were used to design the MIA-system for assessing the 5-year survival of patients with laryngeal cancer. MIA-system accuracy was about 90 % and 85 %, employing the LOO and the Bootstrap methods, respectively. The image texture of p63-expressed nuclei appeared coarser and contained more edges in the 5-year non-survivor group. These differences were at a statistically significant level (p < 0.05). In conclusion, this study has proposed an MIA-system that may be of assistance to physicians, as a second opinion tool in assessing the 5-year survival of patients with laryngeal cancer, and it has revealed useful information regarding differences in nuclei texture between 5-year survivors and non-survivors.

Evaluation of lymph node aspirates at diagnosis and relapse in dogs with high-grade multicentric lymphoma and comparison with survival time

BACKGROUND

Canine high-grade multicentric lymphoma, a common disease with variable response to chemotherapy, is often diagnosed using cytology.

OBJECTIVES

The purpose of the study was to compare cytologic features of canine peripheral lymph node aspirates collected at diagnosis and at relapse, and evaluate their usefulness in predicting survival.

METHODS

Cytologic scoring based on a rubric and nuclear morphometry analyses were performed on cytologic smears collected at diagnosis and at relapse. Scores at diagnosis and relapse were compared by paired t-test and evaluated in relation to time from diagnosis to remission, remission to relapse, relapse to death, and total survival time, using the Cox proportional-hazards regression model.

RESULTS

Number of mitoses and total cytologic score were significantly higher at relapse compared to diagnosis (P < .05). None of the nuclear morphometry measures were significantly different between diagnosis and relapse. The presence of binucleated or multinucleated cells at diagnosis was associated with a shorter remission and decreased total survival (P < .05). Increased mean nucleoli at relapse was associated with longer remission and total survival (P < .05). Increased minimum nuclear radius and diameter at diagnosis were associated with a decreased time from relapse to death (P < .05). Several nuclear morphometry measures at relapse were associated with a shorter time from diagnosis to remission (P < .05).

CONCLUSIONS

Number of mitoses and total score were higher at relapse than at diagnosis in canine lymphoma. The presence of binucleated or multinucleated cells at diagnosis may be useful as indicator of a poor prognosis. Further studies including a larger number of cases are required to reinforce the prognostic values of these cytologic features.

Characterization of squamous cell carcinomas of the head and neck using methods of spatial statistics

In the present study, 53 cases of squamous cell carcinomas of the head and neck were characterized by a quantitative histological texture analysis based on principles of spatial statistics. A planar tessellation of the epithelial tumour component was generated by a skeletonization algorithm. The size distribution of the virtual cells of this planar tessellation, and the size distribution of the profiles of the tumour cell nuclei were estimated in terms of area and boundary length. The intensity, the reduced second moment function (K-function) and the pair correlation function of the point process of the centroids of the profiles of the tumour cell nuclei were also estimated. For both purposes, it is necessary to correct for edge effects, which we consider in this paper in some detail. Specifically, the point patterns of the tumour cell nuclei were considered as realizations of a point process, where the points exist only in the epithelial tumour component (the permitted phase) and not in the stroma (the forbidden phase). The methods allow to characterize each individual tumour by a series of summary statistics. The total set of cases was then partitioned into two groups: 19 cases without lymph node metastases (pN0), and 34 nodal positive cases (pN1 or pN2). Statistical analysis showed no significant differences between the intensities, the mean K-functions and the mean pair correlation functions of the tumour cell nucleus profiles of the two groups. However, there were some significant differences between the sizes of the virtual cells and of the nucleus profiles of the nodal negative cases as compared to the nodal positive cases. In a logistic regression analysis, one of the quantitative nuclear size variables (mean nuclear area) was found to be a significant predictor of lymph node metastasis, in addition to tumour stage. The study shows the potential of methods of spatial statistics for objective quantitative grading of squamous cell carcinomas of the head and neck, and provides an example for modelling histological point patterns as realizations of planar point processes occupying a reference phase which is only a partial component of the total tissue.

Computer based correlation of the texture of P63 expressed nuclei with histological tumour grade, in laryngeal carcinomas

Background. P63 immunostaining has been considered as potential prognostic factor in laryngeal cancer. Considering that P63 is mainly nuclear stain, a possible correlation between the texture of P63-stained nuclei and the tumor's grade could be of value to diagnosis, since this may be related to biologic information imprinted as texture on P63 expressed nuclei. Objective. To investigate the association between P63 stained nuclei and histologic grade in laryngeal tumor lesions. Methods. Biopsy specimens from laryngeal tumour lesions of 55 patients diagnosed with laryngeal squamous cell carcinomas were immunohistochemically (IHC) stained for P63 expression. Four images were digitized from each patient's IHC specimens. P63 positively expressed nuclei were identified, the percentage of P63 expressed nuclei was computed, and 118 textural, morphological, shape, and architectural features were calculated from each one of the 55 laryngeal lesions. Data were split into the low grade (21 grade I lesions) and high grade (34 grade II and grade III lesions) classes for statistical analysis. Results. With advancing grade, P63 expression decreased, P63 stained nuclei appeared of lower image intensity, more inhomogeneous, of higher local contrast, contained smaller randomly distributed dissimilar structures and had irregular shape. Conclusion. P63 expressed nuclei contain important information related to histologic grade.

Morphometric analysis of CD34-positive vessels in salivary gland adenoid cystic and mucoepidermoid carcinomas

BACKGROUND

Carcinomas of the salivary glands are uncommon and morphologically a diverse group of malignancies. To evaluate the prognostic value of CD34 immunostaining of the vessels in adenoid cystic carcinoma (AdCC) and mucoepidermoid carcinoma (MEC), an automated image analysis method was used.

METHOD

In a nationwide study, covering salivary gland cancer (SGC) patients in Finland 1991-1996, 37 AdCC and 18 MEC patients (M 25, F 30, age 25-90, mean 63) were included. In addition to clinical characteristics the size, shape, staining intensity and vessel density in CD34 immunostained histologic samples were measured.

RESULTS

Altogether 4433 vessels were measured from AdCC and 2615 from MEC tumor. Of the total tumor vessels measured, 2651 were from patients who deceased with disease (Group I) and 4397 were from specimens derived from those who did not die of disease (Group II) during the 10-year follow-up. The staining intensity was significantly higher in MEC than in AdCC tumor (P = 0.0005). In MEC, the Group I patients had a higher staining intensity among high-grade patients compared with patients with low grade disease, whereas the tumors in Group II had a lower staining intensity among the high-grade compared with the low grade tumors (P = 0.018). A higher vessel density was found in patients with MEC in group II compared with group I (P = 0.017).

CONCLUSIONS

The staining intensity of CD34 positive vessels in MEC was higher than in AdCC. In MEC, higher staining intensity of vessels in high-grade tumors and lower vessel density in all MEC patients, predicted poor survival.

Nuclear morphometric features in benign breast tissue and risk of subsequent breast cancer

Certain nuclear morphometric features measured in breast tumor tissue have been shown to predict the prognosis of breast cancer patients. However, the application of these features to predicting risk of breast cancer development has received little attention. We conducted a case-control study to evaluate nuclear morphometric features in benign breast tissue in association with subsequent breast cancer risk. The study was nested within a cohort of 4,888 women with a histopathologic diagnosis of benign breast disease (BBD) and involved 61 cases and 71 controls, amongst whom there were 53 matched case-control sets. Conditional logistic regression models were fitted to assess various measurements of nuclear size and nuclear shape factors in relation to subsequent breast cancer risk. In multivariate analysis, subsequent breast cancer risk was positively associated with a nuclear shape factor that takes the shortest nuclear axis and the longest nuclear axis into consideration simultaneously (highest quartile versus lowest 3 quartiles: odds ratio = 3.07, 95% confidence limits = 1.61, 5.84). In contrast, there was no alteration in subsequent breast cancer risk in association with nuclear size features and other shape factors. In conclusion, our study results suggest that the shape factor that takes both the shortest nuclear axis and the longest nuclear axis into consideration might be of value to predict subsequent development of breast cancer among women with BBD.

Nuclear morphometry for the prediction of regional lymph nodes metastases in patients with cancer of the larynx

The changes in cell nuclei reflect their activity. Quantitative morphometric analyses of tumor nuclei could be instrumental in providing prognostic information. We studied whether, and if so, which specific nuclear parameters and histoclinical factors in patients with cancer of the larynx could be related to the lymph node metastases. Specimens were taken from 61 patients surgically treated in the Department of Otolaryngology, Jagiellonian University, Cracow, Poland, between 1987 and 1988. The period between the onset of the first symptoms and the actual commencement of the treatment spanned no more than 9 months. The follow-up period was no shorter than 5 years. Histologically confirmed metastases in the regional lymph nodes were found in 16 patients. The histologic grading and tumor front grading was pursued in all cases. Fourteen parameters of the nuclei were studied with the aid of a computer-assisted system of image analysis. The morphometric parameters and the histoclinical factors were analyzed by the chi(2) test and the stepwise logistic regression. It was established that nuclear area > or =66 microm (P = 0.042), perimeter > or =32 microm (P = 0.087), optical density > or =22,500 (P = 0.027), long axis > or =10.15 microm (P = 0.025), short axis > or =7.3 microm (P = 0.003), TFG assessed (> or =15 points) and tumor advancement (T3, T4) were related to more frequent metastases to the lymph nodes. The morphometric parameters of the greatest significance were short axis and optical density. The quantitative morphometric analysis could prove a useful tool in predicting metastases to the lymph nodes.