Touseef Ur Rehman
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Touseef Ur Rehman has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Meijin Guo
State Key Laboratory of Bioreactor Engineering, East China University of Science and Technology
3 shared publications - Ali Mohsin
State Key Laboratory of Bioreactor Engineering, East China University of Science and Technology, Shanghai 200237, PR China
2 shared publications - Francesca Aiello
University of Calabria
2 shared publications - Huiliang Li
Hangzhou Huaningxiang Biotechnology Co., Ltd., Hangzhou 310000, China
2 shared publications - Kamran Ashraf
State Key Laboratory of Bioreactor Engineering, East China University of Science and Technology, 130 Meilong Road, Shanghai 200237, China
2 shared publications - Luigi Esposito
Department of Bioscience and Technology for Food, Agriculture and Environment, University of Teramo, Via Balzarini 1, 64100 Teramo, Italy
2 shared publications
Latest Publications
- Open Access
- 4 September 2026
- Published by MDPI AG in Technologies
- Vol. 14 (9) , 551
MC-SlotNet: Multiplicity-Consistent Slot-Based Full-Cell Instance Segmentation for Overlapping Plant Suspension-Culture Microscopy
Overlapping cells in plant suspension-culture microscopy pose a particular challenge, for instance, segmentation because a single pixel may belong to more than one cell. Most standard instance-segmentation methods are not designed for this setting and tend to treat overlapping objects as mutually exclusive regions. We instead represent each cell as an independent full-cell instance and introduce MC-SlotNet, an architecture that separates competitive object-slot feature assignment from mask decoding. This allows multiple predicted masks to occupy the same image region. We further introduce a mask-level multiplicity-consistency loss that encourages the predicted number of masks covering a pixel to agree with the underlying cell occupancy. We evaluate MC-SlotNet on a newly annotated dataset of 53 Siraitia grosvenorii suspension-culture micrographs containing 4131 full-cell instances acquired at 4×–40× magnification. Using grouped five-fold cross-validation and an overlap-preserving evaluation protocol, we compare the method with Mask R-CNN, SOLOv2, and Mask2Former. MC-SlotNet achieves the best performance on AP50 (0.800), mAP (0.565), F150 (0.842), all-ground-truth Dice (0.761), AJI+ (0.754), overlap-region Dice (0.705), and overlap-instance recall (0.828). Its AP75 (0.649) is comparable to Mask2Former’s (0.651). MC-SlotNet also has the lowest inference time among the evaluated methods, at 1.113 s/image. These results indicate that decoding full-cell masks independently, rather than enforcing an exclusive partition of image pixels, is well-suited to instance segmentation in plant suspension-culture microscopy images with substantial cell overlap.- 4 September 2026
- Published by MDPI AG in Technologies
- Vol. 14 (9) , 551
Open AccessMC-SlotNet: Multiplicity-Consistent Slot-Based Full-Cell Instance Segmentation for Overlapping Plant Suspension-Culture Microscopy
Overlapping cells in plant suspension-culture microscopy pose a particular challenge, for instance, segmentation because a single pixel may belong to more than one cell. Most standard instance-segmentation methods are not designed for this setting and tend to treat overlapping objects as mutually exclusive regions. We instead represent each cell as an independent full-cell instance and introduce MC-SlotNet, an architecture that separates competitive object-slot feature assignment from mask decoding. This allows multiple predicted masks to occupy the same image region. We further introduce a mask-level multiplicity-consistency loss that encourages the predicted number of masks covering a pixel to agree with the underlying cell occupancy. We evaluate MC-SlotNet on a newly annotated dataset of 53 Siraitia grosvenorii suspension-culture micrographs containing 4131 full-cell instances acquired at 4×–40× magnification. Using grouped five-fold cross-validation and an overlap-preserving evaluation protocol, we compare the method with Mask R-CNN, SOLOv2, and Mask2Former. MC-SlotNet achieves the best performance on AP50 (0.800), mAP (0.565), F150 (0.842), all-ground-truth Dice (0.761), AJI+ (0.754), overlap-region Dice (0.705), and overlap-instance recall (0.828). Its AP75 (0.649) is comparable to Mask2Former’s (0.651). MC-SlotNet also has the lowest inference time among the evaluated methods, at 1.113 s/image. These results indicate that decoding full-cell masks independently, rather than enforcing an exclusive partition of image pixels, is well-suited to instance segmentation in plant suspension-culture microscopy images with substantial cell overlap. - Open Access
- 4 July 2025
- Published by MDPI AG in Pharmaceuticals
- Vol. 18 (7) , 1005
Plant-Derived Exosomes: Nano-Inducers of Cross-Kingdom Regulations
Exosomes are essential components produced by all cell types, originating from the endosomal pathway through the invagination of the cell membrane. Their unique physicochemical characteristics are crucial for various commercial applications. Typically, exosomes range in size from 50 to 200 nm. Exosomes derived from plant cells are larger than their animal cell counterparts and demonstrate a broader therapeutic potential. This review explores the promising research opportunities associated with plant-derived exosomes, summarizing studies on their biogenesis, characterization, isolation methods, and therapeutic applications. It also emphasizes the importance of targeted drug delivery and provides insights into engineering plant-derived exosomes with various drugs. Additionally, highlights of plant-derived exosomes as natural nano-inducers that facilitate inter-kingdom communication and cross-kingdom regulatory interactions are also elucidated herein. Henceforth, this study culminates in a multidimensional insight for innovative therapeutic strategies and biotechnological advancements in plant-derived exosome research.
- 4 July 2025
- Published by MDPI AG in Pharmaceuticals
- Vol. 18 (7) , 1005
Open AccessPlant-Derived Exosomes: Nano-Inducers of Cross-Kingdom Regulations
Exosomes are essential components produced by all cell types, originating from the endosomal pathway through the invagination of the cell membrane. Their unique physicochemical characteristics are crucial for various commercial applications. Typically, exosomes range in size from 50 to 200 nm. Exosomes derived from plant cells are larger than their animal cell counterparts and demonstrate a broader therapeutic potential. This review explores the promising research opportunities associated with plant-derived exosomes, summarizing studies on their biogenesis, characterization, isolation methods, and therapeutic applications. It also emphasizes the importance of targeted drug delivery and provides insights into engineering plant-derived exosomes with various drugs. Additionally, highlights of plant-derived exosomes as natural nano-inducers that facilitate inter-kingdom communication and cross-kingdom regulatory interactions are also elucidated herein. Henceforth, this study culminates in a multidimensional insight for innovative therapeutic strategies and biotechnological advancements in plant-derived exosome research.
- Open Access
- 26 July 2024
- Published by MDPI AG in Preprints.org
Plant-Derived Exosomes: Nano-Inducers of Cross Kingdom Regulations
Exosomes are produced by all cell types, their biogenesis is of endosomal origin, originating as a result of cell membrane invagination. Furthermore, physiochemical characteristics are important prerequisites for their commercial application. The representative size range of exosomes is 50-200 nm. Whereas, comparative to animal cell, exosomes from plant cell sources have a relatively larger size range, moreover, exhibit broader therapeutic potential. In this review study, we have briefly discussed the research potential of plant-derived exosomes. Including their earlier studies on biogenesis, characterization, isolation methods, and possible therapeutic applications. Additionally, we have quoted targeted drug delivery for targeted therapies and have provided insights of methods for customizing exosomes produced from plants with various drugs. Most-importantly, here we have embodied exosomes from plant sources are natural nano-inducers possessing the ability for inter-kingdom communication, resulting in cross-kingdom regulations.
- 26 July 2024
- Published by MDPI AG in Preprints.org
Open AccessPlant-Derived Exosomes: Nano-Inducers of Cross Kingdom Regulations
Exosomes are produced by all cell types, their biogenesis is of endosomal origin, originating as a result of cell membrane invagination. Furthermore, physiochemical characteristics are important prerequisites for their commercial application. The representative size range of exosomes is 50-200 nm. Whereas, comparative to animal cell, exosomes from plant cell sources have a relatively larger size range, moreover, exhibit broader therapeutic potential. In this review study, we have briefly discussed the research potential of plant-derived exosomes. Including their earlier studies on biogenesis, characterization, isolation methods, and possible therapeutic applications. Additionally, we have quoted targeted drug delivery for targeted therapies and have provided insights of methods for customizing exosomes produced from plants with various drugs. Most-importantly, here we have embodied exosomes from plant sources are natural nano-inducers possessing the ability for inter-kingdom communication, resulting in cross-kingdom regulations.