Colorectal cancer risk stratification on histological slides based on survival curves predicted by deep learning.

Studies have shown that colorectal cancer prognosis can be predicted by deep learning-based analysis of histological tissue sections of the primary tumor. So far, this has been achieved using a binary prediction. Survival curves might contain more detailed information and thus enable a more fine-grained risk prediction. Therefore, we established survival curve-based CRC survival predictors and benchmarked them against standard binary survival predictors, comparing their performance extensively on the clinical high and low risk subsets of one internal and three external cohorts. Survival curve-based risk prediction achieved a very similar risk stratification to binary risk prediction for this task. Exchanging other components of the pipeline, namely input tissue and feature extractor, had largely identical effects on model performance independently of the type of risk prediction. An ensemble of all survival curve-based models exhibited a more robust performance, as did a similar ensemble based on binary risk prediction. Patients could be further stratified within clinical risk groups. However, performance still varied across cohorts, indicating limited generalization of all investigated image analysis pipelines, whereas models using clinical data performed robustly on all cohorts.

A self-supervised vision transformer to predict survival from histopathology in renal cell carcinoma.

PURPOSE: To develop and validate an interpretable deep learning model to predict overall and disease-specific survival (OS/DSS) in clear cell renal cell carcinoma (ccRCC). METHODS: Digitised haematoxylin and eosin-stained slides from The Cancer Genome Atlas were used as a training set for a vision transformer (ViT) to extract image features with a self-supervised model called DINO (self-distillation with no labels). Extracted features were used in Cox regression models to prognosticate OS and DSS. Kaplan-Meier for univariable evaluation and Cox regression analyses for multivariable evaluation of the DINO-ViT risk groups were performed for prediction of OS and DSS. For validation, a cohort from a tertiary care centre was used. RESULTS: A significant risk stratification was achieved in univariable analysis for OS and DSS in the training (n = 443, log rank test, p < 0.01) and validation set (n = 266, p < 0.01). In multivariable analysis, including age, metastatic status, tumour size and grading, the DINO-ViT risk stratification was a significant predictor for OS (hazard ratio [HR] 3.03; 95%-confidence interval [95%-CI] 2.11-4.35; p < 0.01) and DSS (HR 4.90; 95%-CI 2.78-8.64; p < 0.01) in the training set but only for DSS in the validation set (HR 2.31; 95%-CI 1.15-4.65; p = 0.02). DINO-ViT visualisation showed that features were mainly extracted from nuclei, cytoplasm, and peritumoural stroma, demonstrating good interpretability. CONCLUSION: The DINO-ViT can identify high-risk patients using histological images of ccRCC. This model might improve individual risk-adapted renal cancer therapy in the future.

Deep learning can predict survival directly from histology in clear cell renal cell carcinoma.

For clear cell renal cell carcinoma (ccRCC) risk-dependent diagnostic and therapeutic algorithms are routinely implemented in clinical practice. Artificial intelligence-based image analysis has the potential to improve outcome prediction and thereby risk stratification. Thus, we investigated whether a convolutional neural network (CNN) can extract relevant image features from a representative hematoxylin and eosin-stained slide to predict 5-year overall survival (5y-OS) in ccRCC. The CNN was trained to predict 5y-OS in a binary manner using slides from TCGA and validated using an independent in-house cohort. Multivariable logistic regression was used to combine of the CNNs prediction and clinicopathological parameters. A mean balanced accuracy of 72.0% (standard deviation [SD] = 7.9%), sensitivity of 72.4% (SD = 10.6%), specificity of 71.7% (SD = 11.9%) and area under receiver operating characteristics curve (AUROC) of 0.75 (SD = 0.07) was achieved on the TCGA training set (n = 254 patients / WSIs) using 10-fold cross-validation. On the external validation cohort (n = 99 patients / WSIs), mean accuracy, sensitivity, specificity and AUROC were 65.5% (95%-confidence interval [CI]: 62.9-68.1%), 86.2% (95%-CI: 81.8-90.5%), 44.9% (95%-CI: 40.2-49.6%), and 0.70 (95%-CI: 0.69-0.71). A multivariable model including age, tumor stage and metastasis yielded an AUROC of 0.75 on the TCGA cohort. The inclusion of the CNN-based classification (Odds ratio = 4.86, 95%-CI: 2.70-8.75, p < 0.01) raised the AUROC to 0.81. On the validation cohort, both models showed an AUROC of 0.88. In univariable Cox regression, the CNN showed a hazard ratio of 3.69 (95%-CI: 2.60-5.23, p < 0.01) on TCGA and 2.13 (95%-CI: 0.92-4.94, p = 0.08) on external validation. The results demonstrate that the CNN's image-based prediction of survival is promising and thus this widely applicable technique should be further investigated with the aim of improving existing risk stratification in ccRCC.

Artificial intelligence to predict oncological outcome directly from hematoxylin and eosin-stained slides in urology.

INTRODUCTION: Artificial intelligence (AI) has been successfully applied for automatic tumor detection and grading in histopathological image analysis in urologic oncology. The aim of this review was to assess the applicability of these approaches in image-based oncological outcome prediction. EVIDENCE ACQUISITION: A systematic literature search was conducted using the databases MEDLINE through PubMed and Web of Science up to April 20, 2021. Studies investigating AI approaches to determine the risk of recurrence, metastasis, or survival directly from H&E-stained tissue sections in prostate, renal cell or urothelial carcinoma were included. Characteristics of the AI approach and performance metrics were extracted and summarized. Risk of bias (RoB) was assessed using the PROBAST tool. EVIDENCE SYNTHESIS: 16 studies yielding a total of 6658 patients and reporting on 17 outcome predictions were included. Six studies focused on renal cell, six on prostate and three on urothelial carcinoma while one study investigated renal cell and urothelial carcinoma. Handcrafted feature extraction was used in five, a convolutional neural network (CNN) in six and a deep feature extraction in four studies. One study compared a CNN with handcrafted feature extraction. In seven outcome predictions, a multivariable comparison with clinicopathological parameters was reported. Five of them showed statistically significant hazard ratios for the AI's model's-prediction. However, RoB was high in 15 outcome predictions and unclear in two. CONCLUSIONS: The included studies are promising but predominantly early pilot studies, therefore primarily highlighting the potential of AI approaches. Additional well-designed studies are needed to assess the actual clinical applicability.

Mobile THz communications using photonic assisted beam steering leaky-wave antennas.

THz communications is envisaged for wide bandwidth mobile communications eventually reaching data capacities exceeding 100 Gbit/s. The technology enabling compact chip-integrated transceivers with highly directive, steerable antennas is the key challenge at THz frequencies to overcome the very high free-space path losses and to support user mobility. In this article, we report on mobile and multi-user THz communications using a photonic THz transmitter chip featuring 1D beam steering for the first time. In the proposed approach, 1D THz beam steering is achieved by using a photodiode excited leaky-wave antenna (LWA) in the transmitter chip. The on-chip LWA allows to steer the directive THz beam from 6° to 39° within the upper WR3-band (0.28-0.33 THz). The antenna's directivity is 14 dBi which is further increased to 23 dBi using an additional hemicylindrical Teflon lens. The 3-dB beam width and coherence bandwidth of the fabricated THz transmitter chips with lens are 9° and 12 GHz, respectively. The proposed approach allows steering the THz beam via the beat frequency of an optical heterodyne system at a speed up to 28°/s. Without using a THz amplifier in the transmitter chip, a data rate of 24 Gbit/s is achieved for a single user for all beam directions and at short wireless distances up to 6 cm. The wireless distance is successfully increased to 32 cm for a lower data rate of 4 Gbit/s, still without using a transmitter amplifier. Also, multi-user THz communications and the overall capacity of the developed THz transmitter chip is studied revealing that up to 12 users could be supported together with a total wireless data capacity of 48 Gbit/s. Fully integrated 2D transmitter chips are expected to reach wireless distances of several meters without additional amplifiers.

Deep learning approach to predict lymph node metastasis directly from primary tumour histology in prostate cancer.

OBJECTIVE: To develop a new digital biomarker based on the analysis of primary tumour tissue by a convolutional neural network (CNN) to predict lymph node metastasis (LNM) in a cohort matched for already established risk factors. PATIENTS AND METHODS: Haematoxylin and eosin (H&E) stained primary tumour slides from 218 patients (102 N+; 116 N0), matched for Gleason score, tumour size, venous invasion, perineural invasion and age, who underwent radical prostatectomy were selected to train a CNN and evaluate its ability to predict LN status. RESULTS: With 10 models trained with the same data, a mean area under the receiver operating characteristic curve (AUROC) of 0.68 (95% confidence interval [CI] 0.678-0.682) and a mean balanced accuracy of 61.37% (95% CI 60.05-62.69%) was achieved. The mean sensitivity and specificity was 53.09% (95% CI 49.77-56.41%) and 69.65% (95% CI 68.21-71.1%), respectively. These results were confirmed via cross-validation. The probability score for LNM prediction was significantly higher on image sections from N+ samples (mean [SD] N+ probability score 0.58 [0.17] vs 0.47 [0.15] N0 probability score, P = 0.002). In multivariable analysis, the probability score of the CNN (odds ratio [OR] 1.04 per percentage probability, 95% CI 1.02-1.08; P = 0.04) and lymphovascular invasion (OR 11.73, 95% CI 3.96-35.7; P < 0.001) proved to be independent predictors for LNM. CONCLUSION: In our present study, CNN-based image analyses showed promising results as a potential novel low-cost method to extract relevant prognostic information directly from H&E histology to predict the LN status of patients with prostate cancer. Our ubiquitously available technique might contribute to an improved LN status prediction.

Ultra-low phase-noise photonic terahertz imaging system based on two-tone square-law detection.

In this paper, we demonstrate a phase-sensitive photonic terahertz imaging system, based on two-tone square-law detection with a record-low phase noise. The system comprises a high-frequency photodiode (PD) for THz generation and a square-law detector (SLD) for THz detection. Two terahertz of approximately 300 GHz tones, separated by an intermediate frequency (IF) (7 GHz-15 GHz), are generated in the PD by optical heterodyning and radiated into free-space. After transmission through a device-under-test, the two-tones are self-mixed inside the SLD. The mixing results in an IF-signal, which still contains the phase information of the terahertz tones. To achieve ultra-low phase-noise, we developed a new mixing scheme using a reference PD and a low-frequency electrical local oscillator (LO) to get rid of additional phase-noise terms. In combination with a second reference PD, the output signal of the SLD can be down-converted to the kHz region to realize lock-in detection with ultra-low phase noise. The evaluation of the phase-noise shows the to-date lowest reported value of phase deviation in a frequency domain photonic terahertz imaging and spectroscopy system of 0.034°. Consequently, we also attain a low minimum detectable path difference of 2 µm for a terahertz difference frequency of 15 GHz. This is in the same range as in coherent single-tone THz systems. At the same time, it lacks their complexity and restrictions caused by the necessary optical LOs, photoconductive antennas, temperature control and delay lines.

Spectral efficient 64-QAM-OFDM terahertz communication link.

We report on a record spectral efficient terahertz communication system using a coherent radio-over-fiber (CRoF) approach. High spectral efficient back-to-back and wireless THz transmission around 325 GHz is experimentally demonstrated using a 64-QAM-OFDM modulation format and a 10 GHz wide wireless channel resulting in a data rate of 59 Gbit/s.