Deep learning (DL) can accelerate the prediction of prognostic biomarkers from routine pathology slides in colorectal cancer (CRC). However, current approaches rely on convolutional neural networks (CNNs) and have mostly been validated on small patient cohorts. Here, we develop a new transformer-based pipeline for end-to-end biomarker prediction from pathology slides by combining a pre-trained transformer encoder with a transformer network for patch aggregation. Our transformer-based approach substantially improves the performance, generalizability, data efficiency, and interpretability as compared with current state-of-the-art algorithms. After training and evaluating on a large multicenter cohort of over 13,000 patients from 16 colorectal cancer cohorts, we achieve a sensitivity of 0.99 with a negative predictive value of over 0.99 for prediction of microsatellite instability (MSI) on surgical resection specimens. We demonstrate that resection specimen-only training reaches clinical-grade performance on endoscopic biopsy tissue, solving a long-standing diagnostic problem.

We design a framework for studying prelinguistic child voice from 3 to 24 months based on state-of-the-art algorithms in diarization. Our system consists of a time-invariant feature extractor, a context-dependent embedding generator, and a classifier. We study the effect of swapping out different components of the system, as well as changing loss function, to find the best performance. We also present a multiple-instance learning technique that allows us to pre-train our parameters on larger datasets with coarser segment boundary labels. We found that our best system achieved 43.8% DER on test dataset, compared to 55.4% DER achieved by LENA software. We also found that using convolutional feature extractor instead of logmel features significantly increases the performance of neural diarization.

Tumor purity is the percentage of cancer cells within a tissue section. Pathologists estimate tumor purity to select samples for genomic analysis by manually reading hematoxylin-eosin (H&E)-stained slides, which is tedious, time consuming, and prone to inter-observer variability. Besides, pathologists\' estimates do not correlate well with genomic tumor purity values, which are inferred from genomic data and accepted as accurate for downstream analysis. We developed a deep multiple instance learning model predicting tumor purity from H&E-stained digital histopathology slides. Our model successfully predicted tumor purity in eight The Cancer Genome Atlas (TCGA) cohorts and a local Singapore cohort. The predictions were highly consistent with genomic tumor purity values. Thus, our model can be utilized to select samples for genomic analysis, which will help reduce pathologists\' workload and decrease inter-observer variability. Furthermore, our model provided tumor purity maps showing the spatial variation within sections. They can help better understand the tumor microenvironment.

BACKGROUND: To reduce the high incidence and mortality of gastric cancer (GC), we aimed to develop deep learning-based models to assist in predicting the diagnosis and overall survival (OS) of GC patients using pathological images.
METHODS: 2333 hematoxylin and eosin-stained pathological pictures of 1037 GC patients were collected from two cohorts to develop our algorithms, Renmin Hospital of Wuhan University (RHWU) and the Cancer Genome Atlas (TCGA). Additionally, we gained 175 digital pictures of 91 GC patients from National Human Genetic Resources Sharing Service Platform (NHGRP), served as the independent external validation set. Two models were developed using artificial intelligence (AI), one named GastroMIL for diagnosing GC, and the other named MIL-GC for predicting outcome of GC.
RESULTS: The discriminatory power of GastroMIL achieved accuracy 0.920 in the external validation set, superior to that of the junior pathologist and comparable to that of expert pathologists. In the prognostic model, C-indices for survival prediction of internal and external validation sets were 0.671 and 0.657, respectively. Moreover, the risk score output by MIL-GC in the external validation set was proved to be a strong predictor of OS both in the univariate (HR = 2.414, P < 0.0001) and multivariable (HR = 1.803, P = 0.043) analyses. The predicting process is available at an online website (https://baigao.github.io/Pathologic-Prognostic-Analysis/).
CONCLUSIONS: Our study developed AI models and contributed to predicting precise diagnosis and prognosis of GC patients, which will offer assistance to choose appropriate treatment to improve the survival status of GC patients.
BACKGROUND: Not applicable.

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

Supervised machine learning is a powerful tool frequently used in computer-aided diagnosis (CAD) applications. The bottleneck of this technique is its demand for fine grained expert annotations, which are tedious for medical image analysis applications. Furthermore, information is typically localized in diagnostic images, which makes representation of an entire image by a single feature set problematic. The multiple instance learning framework serves as a remedy to these two problems by allowing labels to be provided for groups of observations, called bags, and assuming the group label to be the maximum of the instance labels within the bag. This setup can effectively be applied to CAD by splitting a given diagnostic image into a Cartesian grid, treating each grid element (patch) as an instance by representing it with a feature set, and grouping instances belonging to the same image into a bag. We quantify the power of existing multiple instance learning methods by evaluating their performance on two distinct CAD applications: (i) Barrett\'s cancer diagnosis and (ii) diabetic retinopathy screening. In the experiments, mi-Graph appears as the best-performing method in bag-level prediction (i.e. diagnosis) for both of these applications that have drastically different visual characteristics. For instance-level prediction (i.e. disease localization), mi-SVM ranks as the most accurate method.