Tissue characterization using fractal dimension of high frequency ultrasound RF time series

Masked Modeling-Based Ultrasound Image Classification via Self-Supervised Learning

Recently, deep learning-based methods have emerged as the preferred approach for ultrasound data analysis. However, these methods often require large-scale annotated datasets for training deep models, which are not readily available in practical scenarios. Additionally, the presence of speckle noise and other imaging artifacts can introduce numerous hard examples for ultrasound data classification. In this paper, drawing inspiration from self-supervised learning techniques, we present a pre-training method based on mask modeling specifically designed for ultrasound data. Our study investigates three different mask modeling strategies: random masking, vertical masking, and horizontal masking. By employing these strategies, our pre-training approach aims to predict the masked portion of the ultrasound images. Notably, our method does not rely on externally labeled data, allowing us to extract representative features without the need for human annotation. Consequently, we can leverage unlabeled datasets for pre-training. Furthermore, to address the challenges posed by hard samples in ultrasound data, we propose a novel hard sample mining strategy. To evaluate the effectiveness of our proposed method, we conduct experiments on two datasets. The experimental results demonstrate that our approach outperforms other state-of-the-art methods in ultrasound image classification. This indicates the superiority of our pre-training method and its ability to extract discriminative features from ultrasound data, even in the presence of hard examples.

Towards targeted ultrasound-guided prostate biopsy by incorporating model and label uncertainty in cancer detection

PURPOSE

Systematic prostate biopsy is widely used for cancer diagnosis. The procedure is blind to underlying prostate tissue micro-structure; hence, it can lead to a high rate of false negatives. Development of a machine-learning model that can reliably identify suspicious cancer regions is highly desirable. However, the models proposed to-date do not consider the uncertainty present in their output or the data to benefit clinical decision making for targeting biopsy.

METHODS

We propose a deep network for improved detection of prostate cancer in systematic biopsy considering both the label and model uncertainty. The architecture of our model is based on U-Net, trained with temporal enhanced ultrasound (TeUS) data. We estimate cancer detection uncertainty using test-time augmentation and test-time dropout. We then use uncertainty metrics to report the cancer probability for regions with high confidence to help the clinical decision making during the biopsy procedure.

RESULTS

Experiments for prostate cancer classification includes data from 183 prostate biopsy cores of 41 patients. We achieve an area under the curve, sensitivity, specificity and balanced accuracy of 0.79, 0.78, 0.71 and 0.75, respectively.

CONCLUSION

Our key contribution is to automatically estimate model and label uncertainty towards enabling targeted ultrasound-guided prostate biopsy. We anticipate that such information about uncertainty can decrease the number of unnecessary biopsy with a higher rate of cancer yield.

Multiple instance learning combined with label invariant synthetic data for guiding systematic prostate biopsy: a feasibility study

PURPOSE

Ultrasound imaging is routinely used in prostate biopsy, which involves obtaining prostate tissue samples using a systematic, yet, non-targeted approach. This approach is blinded to individual patient intraprostatic pathology, and unfortunately, has a high rate of false negatives.

METHODS

In this paper, we propose a deep network for improved detection of prostate cancer in systematic biopsy. We address several challenges associated with training such network: (1) Statistical labels: Since biopsy core's pathology report only represents a statistical distribution of cancer within the core, we use multiple instance learning (MIL) networks to enable learning from ultrasound image regions associated with those data; (2) Limited labels: The number of biopsy cores are limited to at most 12 per patient. As a result, the number of samples available for training a deep network is limited. We alleviate this issue by effectively combining Independent Conditional Variational Auto Encoders (ICVAE) with MIL. We train ICVAE to learn label-invariant features of RF data, which is subsequently used to generate synthetic data for improved training of the MIL network.

RESULTS

Our in vivo study includes data from 339 prostate biopsy cores of 70 patients. We achieve an area under the curve, sensitivity, specificity, and balanced accuracy of 0.68, 0.77, 0.55 and 0.66, respectively.

CONCLUSION

The proposed approach is generic and can be applied to several other scenarios where unlabeled data and noisy labels in training samples are present.

Measurement of 18F-FDG PET tumor heterogeneity improves early assessment of response to bevacizumab compared with the standard size and uptake metrics in a colorectal cancer model

PURPOSE

Treatment of metastatic colorectal cancer frequently includes antiangiogenic agents such as bevacizumab. Size measurements are inadequate to assess treatment response to these agents, and newer response assessment criteria are needed. We aimed to evaluate F-FDG PET-derived texture parameters in a preclinical colorectal cancer model as alternative metrics of response to treatment with bevacizumab.

MATERIALS AND METHODS

Fourteen CD1 athymic mice injected in the flank with 5×106 LS174T cells (human colorectal carcinoma) were either untreated controls (n=7) or bevacizumab treated (n=7). After 2 weeks, mice underwent F-FDG PET/CT. Calliper-measured tumor growth (Δvol) and final tumor volume (Volcal), F-FDG PET metabolically active volume (Volmet), mean metabolism (Metmean), and maximum metabolism (Metmax) were measured. Twenty-four texture features were compared between treated and untreated mice. Immunohistochemical mean tumor vascular density was estimated by anti-CD-34 staining after tumor resection.

RESULTS

Treated mice had significantly lower tumor vascular density (P=0.032), confirming the antiangiogenic therapeutic effect of bevacizumab. None of the conventional measures were different between the two groups: Δvol (P=0.9), Volcal (P=0.7), Volmet (P=0.28), Metmax (P=0.7), or Metmean (P=0.32). One texture parameter, GLSZM-SZV (visually indicating that the F-FDG PET images of treated mice comprise uniformly sized clusters of different activity) had significantly different means between the two groups of mice (P=0.001).

CONCLUSION

F-FDG PET derived texture parameters, particularly GLSZM-SZV, may be valid biomarkers of tumor response to treatment with bevacizumab, before change in volume.

Investigation of Physical Phenomena Underlying Temporal-Enhanced Ultrasound as a New Diagnostic Imaging Technique: Theory and Simulations

Temporal-enhanced ultrasound (TeUS) is a novel noninvasive imaging paradigm that captures information from a temporal sequence of backscattered US radio frequency data obtained from a fixed tissue location. This technology has been shown to be effective for classification of various in vivo and ex vivo tissue types including prostate cancer from benign tissue. Our previous studies have indicated two primary phenomena that influence TeUS: 1) changes in tissue temperature due to acoustic absorption and 2) micro vibrations of tissue due to physiological vibration. In this paper, first, a theoretical formulation for TeUS is presented. Next, a series of simulations are carried out to investigate micro vibration as a source of tissue characterizing information in TeUS. The simulations include finite element modeling of micro vibration in synthetic phantoms, followed by US image generation during TeUS imaging. The simulations are performed on two media, a sparse array of scatterers and a medium with pathology mimicking scatterers that match nuclei distribution extracted from a prostate digital pathology data set. Statistical analysis of the simulated TeUS data shows its ability to accurately classify tissue types. Our experiments suggest that TeUS can capture the microstructural differences, including scatterer density, in tissues as they react to micro vibrations.

Ultrasonic RF time series for early assessment of the tumor response to chemotherapy

Ultrasound radio-frequency (RF) time series have been shown to carry tissue typing information. To evaluate the potential of RF time series for early prediction of tumor response to chemotherapy, 50MCF-7 breast cancer-bearing nude mice were randomized to receive cisplatin and paclitaxel (treatment group; n = 26) or sterile saline (control group; n = 24). Sequential ultrasound imaging was performed on days 0, 3, 6, and 8 of treatment to simultaneously collect B-mode images and RF data. Six RF time series features, slope, intercept, S1, S2, S3, and S4, were extracted during RF data analysis and contrasted with microstructural tumor changes on histopathology. Chemotherapy administration reduced tumor growth relative to control on days 6 and 8. Compared with day 0, intercept, S1, and S2 were increased while slope was decreased on days 3, 6, and 8 in the treatment group. Compared with the control group, intercept, S1, S2, S3, and S4 were increased, and slope was decreased, on days 3, 6, and 8 in the treatment group. Tumor cell density decreased significantly in the latter on day 3. We conclude that ultrasonic RF time series analysis provides a simple way to noninvasively assess the early tumor response to chemotherapy.

Stochastic Modeling of Temporal Enhanced Ultrasound: Impact of Temporal Properties on Prostate Cancer Characterization

OBJECTIVES

Temporal enhanced ultrasound (TeUS) is a new ultrasound-based imaging technique that provides tissue-specific information. Recent studies have shown the potential of TeUS for improving tissue characterization in prostate cancer diagnosis. We study the temporal properties of TeUS-temporal order and length-and present a new framework to assess their impact on tissue information.

METHODS

We utilize a probabilistic modeling approach using hidden Markov models (HMMs) to capture the temporal signatures of malignant and benign tissues from TeUS signals of nine patients. We model signals of benign and malignant tissues (284 and 286 signals, respectively) in their original temporal order as well as under order permutations. We then compare the resulting models using the Kullback-Liebler divergence and assess their performance differences in characterization. Moreover, we train HMMs using TeUS signals of different durations and compare their model performance when differentiating tissue types.

RESULTS

Our findings demonstrate that models of order-preserved signals perform statistically significantly better (85% accuracy) in tissue characterization compared to models of order-altered signals (62% accuracy). The performance degrades as more changes in signal order are introduced. Additionally, models trained on shorter sequences perform as accurately as models of longer sequences.

CONCLUSION

The work presented here strongly indicates that temporal order has substantial impact on TeUS performance; thus, it plays a significant role in conveying tissue-specific information. Furthermore, shorter TeUS signals can relay sufficient information to accurately distinguish between tissue types.

SIGNIFICANCE

Understanding the impact of TeUS properties facilitates the process of its adopting in diagnostic procedures and provides insights on improving its acquisition.

Tissue typing using ultrasound RF time series: experiments with animal tissue samples

PURPOSE

This article provides experimental evidence to show that the time series of radiofrequency (RF) ultrasound data can be used for tissue typing. It also explores the tissue typing information in RF time series. Clinical and high-frequency ultrasound are studied.

METHODS

Bovine liver, pig liver, bovine muscle, and chicken breast were used in the experiments as the animal tissue types. In the proposed approach, the authors record RF echo signals backscattered from tissue, while the imaging probe and the tissue are stationary. This sequence of recorded RF data generates a time series of RF echoes for each spatial sample of the RF signal. The authors use spectral and fractal features of ultrasound RF time series averaged over a region of interest, along with feedforward neural networks for tissue typing. The experiments are repeated at ultrasound frequency of 6.6 and also 55 MHz. The effects of increasing power and frame rate are studied.

RESULTS

The methodology yielded an average two-class classification accuracy of 95.1% when ultrasound data were acquired at 6.6 MHz and 98.1% when data were collected with a high-frequency probe operating at 55 MHz. In four-class classification experiments, the recorded accuracies were 78.6% and 86.5% for low and high-frequency ultrasound data, respectively. A set of 12 texture features extracted from the B-mode image equivalents of the RF data yields an accuracy of only 77.5% in typing the analyzed tissues. An increase in acoustic power and the frame rate of ultrasound results in an improvement in classification results.

CONCLUSIONS

The results of this study demonstrate that RF time series can be used for ultrasound-based tissue typing. Further investigation of the underlying physical mechanisms is necessary.

Measurement of the skin-liver capsule distance on ultrasound RF data for 1D transient elastography

Vibration-controlled transient elastography (VCTETM) technique is routinely used in clinical practice to assess non-invasively the liver stiffness which is correlated to hepatic fibrosis. Adequate use of the VCTETM probe requires the knowledge of the distance between the skin and the liver parenchyma. This paper compares two methods to estimate this distance using spatial variations of the spectral content of ultrasound radiofrequency (RF) lines, obtained from a probe consisting of a single element ultrasound transducer placed in front of the liver right lobe. Results on a database of 188 patients, including normal-weight and obese persons, show that the spectral variance can accurately discriminate the subcutaneous fat from the liver tissue. The proposed algorithm works in real-time and is suitable for VCTETM scanning protocol setup.

Augmenting detection of prostate cancer in transrectal ultrasound images using SVM and RF time series

We propose a novel and accurate method based on ultrasound RF time series analysis and an extended version of support vector machine classification for generating probabilistic cancer maps that can augment ultrasound images of prostate and enhance the biopsy process. To form the RF time series, we record sequential ultrasound RF echoes backscattered from tissue while the imaging probe and the tissue are stationary in position. We show that RF time series acquired from agar-gelatin-based tissue mimicking phantoms, with difference only in the size of cell-mimicking microscopic glass beads, are distinguishable with statistically reliable accuracies up to 80.5%. This fact indicates that the differences in tissue microstructures affect the ultrasound RF time series features. Based on this phenomenon, in an ex vivo study involving 35 prostate specimens, we show that the features extracted from RF time series are significantly more accurate and sensitive compared to two other established categories of ultrasound-based tissue typing methods. We report an area under receiver operating characteristic curve of 0.95 in tenfold cross validation and 0.82 in leave-one-patient-out cross validation for detection of prostate cancer.

Prostate cancer probability maps based on ultrasound RF time series and SVM classifiers

We describe a very efficient method based on ultrasound RF time series analysis and support vector machine classification for generating probabilistic prostate cancer colormaps to augment the biopsy process. To form the RF time series, we continuously record ultrasound RF echoes backscattered from tissue while the imaging probe and the tissue are stationary in position. In an in-vitro study involving 30 prostate specimens, we show that the features extracted from RF time series are significantly more accurate and sensitive compared to two other established categories of ultrasound-based tissue typing methods. The method results in an area under ROC curve of 0.95 in 10-fold cross-validation.