Manuel Schultheiss

Tina Dorosti, Manuel Schultheiss, Felix Hofmann et al.

We aim to optimize the binary detection of Chronic Obstructive Pulmonary Disease (COPD) based on emphysema presence in the lung with convolutional neural networks (CNN) by exploring manually adjusted versus automated window-setting optimization (WSO) on computed tomography (CT) images. 7,194 CT images (3,597 with COPD; 3,597 healthy controls) from 78 subjects were selected retrospectively (10.2018-12.2021) and preprocessed. For each image, intensity values were manually clipped to the emphysema window setting and a baseline 'full-range' window setting. Class-balanced train, validation, and test sets contained 3,392, 1,114, and 2,688 images. The network backbone was optimized by comparing various CNN architectures. Furthermore, automated WSO was implemented by adding a customized layer to the model. The image-level area under the Receiver Operating Characteristics curve (AUC) [lower, upper limit 95% confidence] was utilized to compare model variations. Repeated inference (n=7) on the test set showed that the DenseNet was the most efficient backbone and achieved a mean AUC of 0.80 [0.76, 0.85] without WSO. Comparably, with input images manually adjusted to the emphysema window, the DenseNet model predicted COPD with a mean AUC of 0.86 [0.82, 0.89]. By adding a customized WSO layer to the DenseNet, an optimal window in the proximity of the emphysema window setting was learned automatically, and a mean AUC of 0.82 [0.78, 0.86] was achieved. Detection of COPD with DenseNet models was improved by WSO of CT data to the emphysema window setting range.

Johannes Thalhammer, Manuel Schultheiss, Tina Dorosti et al.

This is a preprint. The latest version has been published here: https://pubs.rsna.org/doi/10.1148/ryai.230275 Purpose: Sparse-view computed tomography (CT) is an effective way to reduce dose by lowering the total number of views acquired, albeit at the expense of image quality, which, in turn, can impact the ability to detect diseases. We explore deep learning-based artifact reduction in sparse-view cranial CT scans and its impact on automated hemorrhage detection. Methods: We trained a U-Net for artefact reduction on simulated sparse-view cranial CT scans from 3000 patients obtained from a public dataset and reconstructed with varying levels of sub-sampling. Additionally, we trained a convolutional neural network on fully sampled CT data from 17,545 patients for automated hemorrhage detection. We evaluated the classification performance using the area under the receiver operator characteristic curves (AUC-ROCs) with corresponding 95% confidence intervals (CIs) and the DeLong test, along with confusion matrices. The performance of the U-Net was compared to an analytical approach based on total variation (TV). Results: The U-Net performed superior compared to unprocessed and TV-processed images with respect to image quality and automated hemorrhage diagnosis. With U-Net post-processing, the number of views can be reduced from 4096 (AUC-ROC: 0.974; 95% CI: 0.972-0.976) views to 512 views (0.973; 0.971-0.975) with minimal decrease in hemorrhage detection (P<.001) and to 256 views (0.967; 0.964-0.969) with a slight performance decrease (P<.001). Conclusion: The results suggest that U-Net based artifact reduction substantially enhances automated hemorrhage detection in sparse-view cranial CTs. Our findings highlight that appropriate post-processing is crucial for optimal image quality and diagnostic accuracy while minimizing radiation dose.

Stefan P. Hein, Manuel Schultheiss, Andrei Gafita et al.

Assessing tumor response to systemic therapies is one of the main applications of PET/CT. Routinely, only a small subset of index lesions out of multiple lesions is analyzed. However, this operator dependent selection may bias the results due to possible significant inter-metastatic heterogeneity of response to therapy. Automated, AI based approaches for lesion tracking hold promise in enabling the analysis of many more lesions and thus providing a better assessment of tumor response. This work introduces a Siamese CNN approach for lesion tracking between PET/CT scans. Our approach is applied on the laborious task of tracking a high number of bone lesions in full-body baseline and follow-up [68Ga]Ga- or [18F]F-PSMA PET/CT scans after two cycles of [177Lu]Lu-PSMA therapy of metastatic castration resistant prostate cancer patients. Data preparation includes lesion segmentation and affine registration. Our algorithm extracts suitable lesion patches and forwards them into a Siamese CNN trained to classify the lesion patch pairs as corresponding or non-corresponding lesions. Experiments have been performed with different input patch types and a Siamese network in 2D and 3D. The CNN model successfully learned to classify lesion assignments, reaching a lesion tracking accuracy of 83 % in its best configuration with an AUC = 0.91. For remaining lesions the pipeline accomplished a re-identification rate of 89 %. We proved that a CNN may facilitate the tracking of multiple lesions in PSMA PET/CT scans. Future clinical studies are necessary if this improves the prediction of the outcome of therapies.

Tina Dorosti, Manuel Schultheiss, Philipp Schmette et al.

Purpose: To estimate the total lung volume (TLV) from real and synthetic frontal chest radiographs (CXR) on a pixel level using lung thickness maps generated by a U-Net deep learning model. Methods: This retrospective study included 5,959 chest CT scans from two public datasets: the lung nodule analysis 2016 (n=656) and the Radiological Society of North America (RSNA) pulmonary embolism detection challenge 2020 (n=5,303). Additionally, 72 participants were selected from the Klinikum Rechts der Isar dataset (October 2018 to December 2019), each with a corresponding chest radiograph taken within seven days. Synthetic radiographs and lung thickness maps were generated using forward projection of CT scans and their lung segmentations. A U-Net model was trained on synthetic radiographs to predict lung thickness maps and estimate TLV. Model performance was assessed using mean squared error (MSE), Pearson correlation coefficient (r), and two-sided Student's t-distribution. Results: The study included 72 participants (45 male, 27 female, 33 healthy: mean age 62 years [range 34-80]; 39 with chronic obstructive pulmonary disease: mean age 69 years [range 47-91]). TLV predictions showed low error rates ($MSE_{Public-Synthetic}$=0.16 $L^2$, $MSE_{KRI-Synthetic}$=0.20 $L^2$, $MSE_{KRI-Real}$=0.35 $L^2$) and strong correlations with CT-derived reference standard TLV ($n_{Public-Synthetic}$=1,191, r=0.99, P<0.001; $n_{KRI-Synthetic}$=72, r=0.97, P<0.001; $n_{KRI-Real}$=72, r=0.91, P<0.001). The Luna16 test data demonstrated the highest performance, with the lowest mean squared error (MSE = 0.09 $L^2$) and strongest correlation (r = 0.99, P <0.001) for TLV estimation. Conclusion: The U-Net-generated pixel-level lung thickness maps successfully estimated TLV for both synthetic and real radiographs.