A Dirichlet process mixture model for automatic (18)F-FDG PET image segmentation: Validation study on phantoms and on lung and esophageal lesions

Artificial intelligence in automatic image segmentation system for exploring recurrence patterns in small cell carcinoma of the lung

Background

The integration of artificial intelligence (AI) in automatic image segmentation systems offers a novel approach to evaluating the clinical target volume (CTV) in small cell lung cancer (SCLC) patients. Utilizing imaging recurrence data, this study applies a recursive feature elimination algorithm to model and predict patient prognoses, aiming to enhance clinical guidance and prediction accuracy.

Materials and Methods

This research analyzed data from SCLC patients who received curative radiotherapy from January 1, 2010, to December 30, 2021, and had comprehensive follow-up records including pre- and post-treatment imaging. An AI-driven image segmentation system segmented the initial CTV, evaluating 110 clinical parameters. The recursive feature elimination method selected pertinent features, and a random forest-based recursive prediction model was developed to establish a clinically viable recurrence prediction model.

Results

1. Local Control Analysis: A study of 180 patients, with a median follow-up duration of 36 months, revealed that 94 experienced recurrences, while 86 did not. Factors influencing local control rates included gender (male), age (>60 years), T stage, smoking index, and tumor size. Notably, tumor size (≥ 5cm) emerged as an independent factor significantly impacting local control rates, with a Hazard Ratio (HR) of 1.635 (95% CI: 1.055-2.536, p=0.028). 2. Recurrence Analysis: Tumor size (≥ 5cm) was also closely linked to patient local control rates, with a 3-year Local Control Rate Failure (LCRF) contrasting sharply between larger tumors (61.1%) and smaller tumors (86.7%, p=0.004). Upon analyzing recurrence patterns among 94 patients, a total of 170 instances were examined. Recurrence was most prevalent in regions 10R, 10L, 4R, and 7, accounting for 67.65% (115/170) of cases, while regions 2L and 3P showed no recurrences. The initial region of the primary tumor or metastatic lymph nodes was identified as a critical recurrence area, with a 100% recurrence rate in patients whose initial tumor region included 10 specific regions. The recurrence rates for initial tumor regions involving 4R, 7, 11R, and 11L ranged between 41.6% and 45.5%. 3. Development of a recurrence prediction model: utilizing an AI-powered automatic image segmentation system, multidimensional partition parameters, including 110 clinical variables, were analyzed. The recursive feature elimination method facilitated efficient feature selection. From this, a recurrence prediction model for small cell lung cancer was developed using a random forest algorithm, achieving a clinically significant accuracy rate of 77%. This model provides a reliable basis for enhancing the clinical application and decision-making process for medical practitioners.

Conclusion

The utilization of AI-based automatic image segmentation system for delineating the initial CTV has proven pivotal. Analysis and modeling of recurrent images reveal that the initial GTV and GTVnd are critical regions for recurrence. Leveraging partition parameter and variable information, we constructed a clinically viable recurrence prediction model. This model significantly aids in guiding the precise clinical targeting of treatment areas, demonstrating the potential of AI to enhance patient management and treatment outcomes in small cell lung cancer.

Comparing the performance of a deep learning-based lung gross tumour volume segmentation algorithm before and after transfer learning in a new hospital

Objectives

Radiation therapy for lung cancer requires a gross tumour volume (GTV) to be carefully outlined by a skilled radiation oncologist (RO) to accurately pinpoint high radiation dose to a malignant mass while simultaneously minimizing radiation damage to adjacent normal tissues. This is manually intensive and tedious however, it is feasible to train a deep learning (DL) neural network that could assist ROs to delineate the GTV. However, DL trained on large openly accessible data sets might not perform well when applied to a superficially similar task but in a different clinical setting. In this work, we tested the performance of DL automatic lung GTV segmentation model trained on open-access Dutch data when used on Indian patients from a large public tertiary hospital, and hypothesized that generic DL performance could be improved for a specific local clinical context, by means of modest transfer-learning on a small representative local subset.

Methods

X-ray computed tomography (CT) series in a public data set called "NSCLC-Radiomics" from The Cancer Imaging Archive was first used to train a DL-based lung GTV segmentation model (Model 1). Its performance was assessed using a different open access data set (Interobserver1) of Dutch subjects plus a private Indian data set from a local tertiary hospital (Test Set 2). Another Indian data set (Retrain Set 1) was used to fine-tune the former DL model using a transfer learning method. The Indian data sets were taken from CT of a hybrid scanner based in nuclear medicine, but the GTV was drawn by skilled Indian ROs. The final (after fine-tuning) model (Model 2) was then re-evaluated in "Interobserver1" and "Test Set 2." Dice similarity coefficient (DSC), precision, and recall were used as geometric segmentation performance metrics.

Results

Model 1 trained exclusively on Dutch scans showed a significant fall in performance when tested on "Test Set 2." However, the DSC of Model 2 recovered by 14 percentage points when evaluated in the same test set. Precision and recall showed a similar rebound of performance after transfer learning, in spite of using a comparatively small sample size. The performance of both models, before and after the fine-tuning, did not significantly change the segmentation performance in "Interobserver1."

Conclusions

A large public open-access data set was used to train a generic DL model for lung GTV segmentation, but this did not perform well initially in the Indian clinical context. Using transfer learning methods, it was feasible to efficiently and easily fine-tune the generic model using only a small number of local examples from the Indian hospital. This led to a recovery of some of the geometric segmentation performance, but the tuning did not appear to affect the performance of the model in another open-access data set.

Advances in knowledge

Caution is needed when using models trained on large volumes of international data in a local clinical setting, even when that training data set is of good quality. Minor differences in scan acquisition and clinician delineation preferences may result in an apparent drop in performance. However, DL models have the advantage of being efficiently "adapted" from a generic to a locally specific context, with only a small amount of fine-tuning by means of transfer learning on a small local institutional data set.

Clinical target volume automatic segmentation based on lymph node stations for lung cancer with bulky lump lymph nodes

Background

The lack of standardized delineation of lymph node station in lung cancer radiotherapy leads to nonstandard clinical target volume (CTV) contouring, especially in patients with bulky lump gross target volume lymph nodes (GTVnd). This study defines lymph node region boundaries in radiotherapy for lung cancer and automatically contours lymph node stations based on the International Association for the Study of Lung Cancer (IASLC) lymph node map.

Methods

Computed tomography (CT) scans of 200 patients with small cell lung cancer were collected. The lymph node zone boundaries were defined based on the IASLC lymph node map, with adjustments to meet radiotherapy requirements. Contours of lymph node stations were confirmed by two experienced oncologists. A model (DiUNet) was constructed by incorporating the contours of GTVnd to precisely contour the boundaries. Quantitative evaluation metrics and clinical evaluations were conducted.

Results

The mean 3D Dice similarity coefficient (Dice similarity coefficient) values of DiUNet in most lymph node stations was greater than 0.7, 98.87% of the lymph node station slices are accepted. The mean DiUNet score was not significantly different from that of the man contoured in the evaluation of lymph node stations and CTV.

Conclusion

This is the first study to propose a method that automatically contours lymph node regions station by station based on the IASLC lymph node map with bulky lump GTVnd. Delineation of lymph node stations based on the DiUNet model is a promising strategy to obtain accuracy and efficiency for CTV delineation in lung cancer patients, especially for bulky lump GTVnd.

Deep Learning Improved Clinical Target Volume Contouring Quality and Efficiency for Postoperative Radiation Therapy in Non-small Cell Lung Cancer

Purpose: To investigate whether a deep learning-assisted contour (DLAC) could provide greater accuracy, inter-observer consistency, and efficiency compared with a manual contour (MC) of the clinical target volume (CTV) for non-small cell lung cancer (NSCLC) receiving postoperative radiotherapy (PORT).

Materials and Methods: A deep dilated residual network was used to achieve the effective automatic contour of the CTV. Eleven junior physicians contoured CTVs on 19 patients by using both MC and DLAC methods independently. Compared with the ground truth, the accuracy of the contour was evaluated by using the Dice coefficient and mean distance to agreement (MDTA). The coefficient of variation (CV) and standard distance deviation (SDD) were rendered to measure the inter-observer variability or consistency. The time consumed for each of the two contouring methods was also compared.

Results: A total of 418 CTV sets were generated. DLAC improved contour accuracy when compared with MC and was associated with a larger Dice coefficient (mean ± SD: 0.75 ± 0.06 vs. 0.72 ± 0.07, p < 0.001) and smaller MDTA (mean ± SD: 2.97 ± 0.91 mm vs. 3.07 ± 0.98 mm, p < 0.001). The DLAC was also associated with decreased inter-observer variability, with a smaller CV (mean ± SD: 0.129 ± 0.040 vs. 0.183 ± 0.043, p < 0.001) and SDD (mean ± SD: 0.47 ± 0.22 mm vs. 0.72 ± 0.41 mm, p < 0.001). In addition, a value of 35% of time saving was provided by the DLAC (median: 14.81 min vs. 9.59 min, p < 0.001).

Conclusions: Compared with MC, the DLAC is a promising strategy to obtain superior accuracy, consistency, and efficiency for the PORT-CTV in NSCLC.