The promise and challenges of deep learning models for automated histopathologic classification and mutation prediction in lung cancer

Revolutionising osseous biopsy: the impact of artificial intelligence in the era of personalized medicine

In a rapidly evolving healthcare environment, artificial intelligence (AI) is transforming diagnostic techniques and personalized medicine. This is also seen in osseous biopsies. AI applications in radiomics, histopathology, predictive modelling, biopsy navigation, and interdisciplinary communication are reshaping how bone biopsies are conducted and interpreted. We provide a brief review of AI in image- guided biopsy of bone tumours (primary and secondary) and specimen handling, in the era of personalized medicine. This article explores AI's role in enhancing diagnostic accuracy, improving safety in biopsies, and enabling more precise targeting in bone lesion biopsies, ultimately contributing to better patient outcomes in personalized medicine. We dive into various AI technologies applied to osseous biopsies, such as traditional machine learning, deep learning, radiomics, simulation, and generative models. We explore their roles in tumour-board meetings, communication between clinicians, radiologists, and pathologists. Additionally, we inspect ethical considerations associated with the integration of AI in bone biopsy procedures, technical limitations, and we delve into health equity, generalizability, deployment issues, and reimbursement challenges in AI-powered healthcare. Finally, we explore potential future developments and offer a list of open-source AI tools and algorithms relevant to bone biopsies, which we include to encourage further discussion and research.

Digital profiling of cancer transcriptomes from histology images with grouped vision attention

Cancer is a heterogeneous disease that demands precise molecular profiling for better understanding and management. Recently, deep learning has demonstrated potentials for cost-efficient prediction of molecular alterations from histology images. While transformer-based deep learning architectures have enabled significant progress in non-medical domains, their application to histology images remains limited due to small dataset sizes coupled with the explosion of trainable parameters. Here, we develop SEQUOIA, a transformer model to predict cancer transcriptomes from whole-slide histology images. To enable the full potential of transformers, we first pre-train the model using data from 1,802 normal tissues. Then, we fine-tune and evaluate the model in 4,331 tumor samples across nine cancer types. The prediction performance is assessed at individual gene levels and pathway levels through Pearson correlation analysis and root mean square error. The generalization capacity is validated across two independent cohorts comprising 1,305 tumors. In predicting the expression levels of 25,749 genes, the highest performance is observed in cancers from breast, kidney and lung, where SEQUOIA accurately predicts the expression of 11,069, 10,086 and 8,759 genes, respectively. The accurately predicted genes are associated with the regulation of inflammatory response, cell cycles and metabolisms. While the model is trained at the tissue level, we showcase its potential in predicting spatial gene expression patterns using spatial transcriptomics datasets. Leveraging the prediction performance, we develop a digital gene expression signature that predicts the risk of recurrence in breast cancer. SEQUOIA deciphers clinically relevant gene expression patterns from histology images, opening avenues for improved cancer management and personalized therapies.

Focalizing regions of biomarker relevance facilitates biomarker prediction on histopathological images

Image-based AI has thrived as a potentially revolutionary tool for predicting molecular biomarker statuses, which aids in categorizing patients for appropriate medical treatments. However, many methods using hematoxylin and eosin-stained (H&E) whole-slide images (WSIs) have been found to be inefficient because of the presence of numerous uninformative or irrelevant image patches. In this study, we introduced the region of biomarker relevance (ROB) concept to identify the morphological areas most closely associated with biomarkers for accurate status prediction. We actualized this concept within a framework called saliency ROB search (SRS) to enable efficient and effective predictions. By evaluating various lung adenocarcinoma (LUAD) biomarkers, we showcased the superior performance of SRS compared to current state-of-the-art AI approaches. These findings suggest that AI tools, built on the ROB concept, can achieve enhanced molecular biomarker prediction accuracy from pathological images.

Evaluation of an Integrated Spectroscopy and Classification Platform for Point-of-Care Core Needle Biopsy Assessment: Performance Characteristics from Ex Vivo Renal Mass Biopsies

PURPOSE

To evaluate a transmission optical spectroscopy instrument for rapid ex vivo assessment of core needle cancer biopsies (CNBs) at the point of care.

MATERIALS AND METHODS

CNBs from surgically resected renal tumors and nontumor regions were scanned on their sampling trays with a custom spectroscopy instrument. After extracting principal spectral components, machine learning was used to train logistic regression, support vector machines, and random decision forest (RF) classifiers on 80% of randomized and stratified data. The algorithms were evaluated on the remaining 20% of the data set held out during training. Binary classification (tumor/nontumor) was performed based on a decision threshold. Multinomial classification was also performed to differentiate between the subtypes of renal cell carcinoma (RCC) and account for potential confounding effects from fat, blood, and necrotic tissue. Classifiers were compared based on sensitivity, specificity, and positive predictive value (PPV) relative to a histopathologic standard.

RESULTS

A total of 545 CNBs from 102 patients were analyzed, yielding 5,583 spectra after outlier exclusion. At the individual spectra level, the best performing algorithm was RF with sensitivities of 96% and 92% and specificities of 90% and 89%, for the binary and multiclass analyses, respectively. At the full CNB level, RF algorithm also showed the highest sensitivity and specificity (93% and 91%, respectively). For RCC subtypes, the highest sensitivity and PPV were attained for clear cell (93.5%) and chromophobe (98.2%) subtypes, respectively.

CONCLUSIONS

Ex vivo spectroscopy imaging paired with machine learning can accurately characterize renal mass CNB at the time of tissue acquisition.

Multisite Tumor Sampling Reveals Extensive Heterogeneity of Tumor and Host Immune Response in Ovarian Cancer

BACKGROUND/AIM

Ovarian cancer (OVCA) is characterized by genomic/molecular intra-patient heterogeneity (IPH). Tissue histology and morphological features are surrogates of the underlying genomic/molecular contexture. We assessed the morphological IPH of OVCA tumor compartments and of lymphocytic infiltrates in multiple matched samples per patient.

MATERIALS AND METHODS

We examined 294 hematoxylin & eosin (H&E) OVCA tumor whole sections from 70 treatment-naïve patients who had undergone cytoreductive surgery. We assessed morphological subtypes as immunoreactive (IR), solid - proliferative (SD), papilloglandular (PG), and mesenchymal transition (MT); subtype load per patient; stromal tumor-infiltrating lymphocyte (sTIL) density as average per sample; and, as maximal sTIL values (max-TILs) among all samples per patient, ovaries and implants.

RESULTS

Among all 294 tumor sections, the most frequent primary morphological subtype was PG (n=150, 51.0%), followed by MT (71, 24.1%), SD (48, 16.3%) and IR (15, 5.1%). Subtype combinations were observed in 67/294 sections (22.8%) and IPH in 48/70 patients (68.6%). PG prevailed in ovaries (p<0.001), SD and MT in implants (p=0.023 and p<0.001, respectively). sTILs were higher in SD compared to non-SD (p=0.019) and lower in PG, respectively (p<0.001). sTIL density was higher in implants than in ovaries (p<0.001). Higher max-TILs were associated with stage IV disease (p=0.043), upper abdominal dissemination (p=0.024), endometrioid histology (p=0.013), and grade 3 tumors (p=0.021). Favorable prognosticators were higher max-TILs per patient (PFS, OS) and higher SD-load (PFS).

CONCLUSION

Clinically relevant morphological and host immune-response IPH appear to be the norm in OVCA. This may complicate efforts to decipher sensitivity of the tumor to certain treatment modalities from a single pre-operative biopsy.